Will's Blog: Study: newer, bigger versions of LLMs like OpenAI's GPT, Meta's Llama, and BigScience's BLOOM are more inclined to give wrong answers than to admit ignorance (Nicola Jones/Nature)

26 September 2024

Study: newer, bigger versions of LLMs like OpenAI's GPT, Meta's Llama, and BigScience's BLOOM are more inclined to give wrong answers than to admit ignorance (Nicola Jones/Nature)

Nicola Jones / Nature:
Study: newer, bigger versions of LLMs like OpenAI's GPT, Meta's Llama, and BigScience's BLOOM are more inclined to give wrong answers than to admit ignorance — - Nicola Jones — You can also search for this author in — PubMed Google Scholar — A study of newer …

Posted from: this blog via Microsoft Power Automate.